Merge tag 'sched-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Energy scheduling:

   - Consolidate how the max compute capacity is used in the scheduler
     and how we calculate the frequency for a level of utilization.

   - Rework interface between the scheduler and the schedutil governor

   - Simplify the util_est logic

  Deadline scheduler:

   - Work more towards reducing SCHED_DEADLINE starvation of low
     priority tasks (e.g., SCHED_OTHER) tasks when higher priority tasks
     monopolize CPU cycles, via the introduction of 'deadline servers'
     (nested/2-level scheduling).

     "Fair servers" to make use of this facility are not introduced yet.

  EEVDF:

   - Introduce O(1) fastpath for EEVDF task selection

  NUMA balancing:

   - Tune the NUMA-balancing vma scanning logic some more, to better
     distribute the probability of a particular vma getting scanned.

  Plus misc fixes, cleanups and updates"

* tag 'sched-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  sched/fair: Fix tg->load when offlining a CPU
  sched/fair: Remove unused 'next_buddy_marked' local variable in check_preempt_wakeup_fair()
  sched/fair: Use all little CPUs for CPU-bound workloads
  sched/fair: Simplify util_est
  sched/fair: Remove SCHED_FEAT(UTIL_EST_FASTUP, true)
  arm64/amu: Use capacity_ref_freq() to set AMU ratio
  cpufreq/cppc: Set the frequency used for computing the capacity
  cpufreq/cppc: Move and rename cppc_cpufreq_{perf_to_khz|khz_to_perf}()
  energy_model: Use a fixed reference frequency
  cpufreq/schedutil: Use a fixed reference frequency
  cpufreq: Use the fixed and coherent frequency for scaling capacity
  sched/topology: Add a new arch_scale_freq_ref() method
  freezer,sched: Clean saved_state when restoring it during thaw
  sched/fair: Update min_vruntime for reweight_entity() correctly
  sched/doc: Update documentation after renames and synchronize Chinese version
  sched/cpufreq: Rework iowait boost
  sched/cpufreq: Rework schedutil governor performance estimation
  sched/pelt: Avoid underestimation of task utilization
  sched/timers: Explain why idle task schedules out on remote timer enqueue
  sched/cpuidle: Comment about timers requirements VS idle handler
  ...

1 files changed, 104 insertions, 0 deletions

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 7ff269a78c208..d155a86a86148 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,6 +39,9 @@
 #include <linux/rwsem.h>
 #include <linux/wait.h>
 #include <linux/topology.h>
+#include <linux/dmi.h>
+#include <linux/units.h>
+#include <asm/unaligned.h>
 
 #include <acpi/cppc_acpi.h>
 
@@ -1760,3 +1763,104 @@ unsigned int cppc_get_transition_latency(int cpu_num)
 	return latency_ns;
 }
 EXPORT_SYMBOL_GPL(cppc_get_transition_latency);
+
+/* Minimum struct length needed for the DMI processor entry we want */
+#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
+
+/* Offset in the DMI processor structure for the max frequency */
+#define DMI_PROCESSOR_MAX_SPEED		0x14
+
+/* Callback function used to retrieve the max frequency from DMI */
+static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
+{
+	const u8 *dmi_data = (const u8 *)dm;
+	u16 *mhz = (u16 *)private;
+
+	if (dm->type == DMI_ENTRY_PROCESSOR &&
+	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
+		u16 val = (u16)get_unaligned((const u16 *)
+				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
+		*mhz = val > *mhz ? val : *mhz;
+	}
+}
+
+/* Look up the max frequency in DMI */
+static u64 cppc_get_dmi_max_khz(void)
+{
+	u16 mhz = 0;
+
+	dmi_walk(cppc_find_dmi_mhz, &mhz);
+
+	/*
+	 * Real stupid fallback value, just in case there is no
+	 * actual value set.
+	 */
+	mhz = mhz ? mhz : 1;
+
+	return KHZ_PER_MHZ * mhz;
+}
+
+/*
+ * If CPPC lowest_freq and nominal_freq registers are exposed then we can
+ * use them to convert perf to freq and vice versa. The conversion is
+ * extrapolated as an affine function passing by the 2 points:
+ *  - (Low perf, Low freq)
+ *  - (Nominal perf, Nominal freq)
+ */
+unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64 mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		mul = caps->nominal_freq - caps->lowest_freq;
+		mul *= KHZ_PER_MHZ;
+		div = caps->nominal_perf - caps->lowest_perf;
+		offset = caps->nominal_freq * KHZ_PER_MHZ -
+			 div64_u64(caps->nominal_perf * mul, div);
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = max_khz;
+		div = caps->highest_perf;
+	}
+
+	retval = offset + div64_u64(perf * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_perf_to_khz);
+
+unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64  mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		mul = caps->nominal_perf - caps->lowest_perf;
+		div = caps->nominal_freq - caps->lowest_freq;
+		/*
+		 * We don't need to convert to kHz for computing offset and can
+		 * directly use nominal_freq and lowest_freq as the div64_u64
+		 * will remove the frequency unit.
+		 */
+		offset = caps->nominal_perf -
+			 div64_u64(caps->nominal_freq * mul, div);
+		/* But we need it for computing the perf level. */
+		div *= KHZ_PER_MHZ;
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = caps->highest_perf;
+		div = max_khz;
+	}
+
+	retval = offset + div64_u64(freq * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_khz_to_perf);